Comment by aenis

3 hours ago

We use a bunch, at the moment we mainly self host (and use pipecat) use Daily, and a few niche boutique suppliers who built things for us.

There is a great resource for learning this stuff - the CEO of Daily, Kwindla Kramer, hosted a series of 1hr sessions on low latency voice ai. Here:

Some of this is a bit outdated but most of it is very valuable.

Kwindla posts a lot of extremely useful stuff on x and linkedin, incl. working, easily replicable sub 500ms setups.

1 comment

aenis

Beautiful thanks. We are also looking at this and another complication is transcripts can get pretty messy updates, corrections etc.